Imagen de Portada

Continuous sentiment scores for literary and multilingual contexts

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lyngbaek, Laurits, Feldkamp, Pascale, Bizzoni, Yuri, Nielbo, Kristoffer, Enevoldsen, Kenneth
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Is Sentiment Banana-Shaped? Exploring the Geometry and Portability of Sentiment Concept Vectors
por: Lyngbaek, Laurits, et al.
Publicado: (2026)

Good Books are Complex Matters: Gauging Complexity Profiles Across Diverse Categories of Perceived Literary Quality
por: Bizzoni, Yuri, et al.
Publicado: (2024)

topicwizard -- a Modern, Model-agnostic Framework for Topic Model Visualization and Interpretation
por: Kardos, Márton, et al.
Publicado: (2025)

The Scandinavian Embedding Benchmarks: Comprehensive Assessment of Multilingual and Monolingual Text Embedding
por: Enevoldsen, Kenneth, et al.
Publicado: (2024)

Naturalistic measure of social norms alignment
por: Kostiuk, Yevhen, et al.
Publicado: (2026)

Says Who? Effective Zero-Shot Annotation of Focalization
por: Hicke, Rebecca M. M., et al.
Publicado: (2024)

Multilingual Embedding Probes Fail to Generalize Across Learner Corpora
por: Lyngbaek, Laurits, et al.
Publicado: (2026)

$S^3$ -- Semantic Signal Separation
por: Kardos, Márton, et al.
Publicado: (2024)

The Coverage Illusion: From Pre-retrieval Routing Failure to Post-retrieval Cascades in a Production RAG System
por: Hussain, Zafar, et al.
Publicado: (2026)

Improving reasoning at inference time via uncertainty minimisation
por: Legrand, Nicolas, et al.
Publicado: (2026)

One prompt is not enough: Instruction Sensitivity Undermines Embedding Model Evaluation
por: Kostiuk, Yevhen, et al.
Publicado: (2026)

Dynaword: From One-shot to Continuously Developed Datasets
por: Enevoldsen, Kenneth, et al.
Publicado: (2025)

DANSK and DaCy 2.6.0: Domain Generalization of Danish Named Entity Recognition
por: Enevoldsen, Kenneth, et al.
Publicado: (2024)

Exposing Assumptions in AI Benchmarks through Cognitive Modelling
por: Rystrøm, Jonathan H., et al.
Publicado: (2024)

Can LLMs reason over extended multilingual contexts? Towards long-context evaluation beyond retrieval and haystacks
por: Hengle, Amey, et al.
Publicado: (2025)

HUME: Measuring the Human-Model Performance Gap in Text Embedding Tasks
por: Assadi, Adnan El, et al.
Publicado: (2025)

One ruler to measure them all: Benchmarking multilingual long-context language models
por: Kim, Yekyung, et al.
Publicado: (2025)

Fine-tuning multilingual language models in Twitter/X sentiment analysis: a study on Eastern-European V4 languages
por: Filip, Tomáš, et al.
Publicado: (2024)

Affect as a proxy for literary mood
por: Öhman, Emily, et al.
Publicado: (2023)

Directional Alignment and Narrative Agency in Human-LLM Co-Writing
por: Fundal, Halfdan Nordahl, et al.
Publicado: (2026)

Encoder vs Decoder: Comparative Analysis of Encoder and Decoder Language Models on Multilingual NLU Tasks
por: Nielsen, Dan Saattrup, et al.
Publicado: (2024)

Maintaining MTEB: Towards Long Term Usability and Reproducibility of Embedding Benchmarks
por: Chung, Isaac, et al.
Publicado: (2025)

The impact of postediting on AI generative translation in Yemeni context: Translating literary prose by ChatGPT
por: Al-wagieh, Nasim, et al.
Publicado: (2026)

Morphosyntactic probing of multilingual BERT models
por: Acs, Judit, et al.
Publicado: (2023)

Grounding Text Embeddings in Stakeholder Associations
por: Rystrøm, Jonathan, et al.
Publicado: (2026)

Contextual effects of sentiment deployment in human and machine translation
por: Comstock, Lindy, et al.
Publicado: (2025)

Probabilistic emotion and sentiment modelling of patient-reported experiences
por: Murray, Curtis, et al.
Publicado: (2024)

What's in a prompt? Language models encode literary style in prompt embeddings
por: Sarfati, Raphaël, et al.
Publicado: (2025)

CIDER: Context sensitive sentiment analysis for short-form text
por: Young, James C., et al.
Publicado: (2023)

Exploring the topics, sentiments and hate speech in the Spanish information environment
por: LOPEZ, ALEJANDRO BUITRAGO, et al.
Publicado: (2024)

Integrated ensemble of BERT- and features-based models for authorship attribution in Japanese literary works
por: Kanda, Taisei, et al.
Publicado: (2025)

Dynamic embedded topic models and change-point detection for exploring literary-historical hypotheses
por: Sirin, Hale, et al.
Publicado: (2024)

Metaphors' journeys across time and genre: tracking the evolution of literary metaphors with temporal embeddings
por: Mangiaterra, Veronica, et al.
Publicado: (2026)

Understanding the role of FFNs in driving multilingual behaviour in LLMs
por: Bhattacharya, Sunit, et al.
Publicado: (2024)

Retrieval-augmented generation in multilingual settings
por: Chirkova, Nadezhda, et al.
Publicado: (2024)

The emojification of sentiment on social media: Collection and analysis of a longitudinal Twitter sentiment dataset
por: Yin, Wenjie, et al.
Publicado: (2021)

Will sentiment analysis need subculture? A new data augmentation approach
por: Wang, Zhenhua, et al.
Publicado: (2023)

Exa-PSD: a new Persian sentiment analysis dataset on Twitter
por: Ghaderi, Seyed Himan, et al.
Publicado: (2026)

Lex2Sent: A bagging approach to unsupervised sentiment analysis
por: Lange, Kai-Robin, et al.
Publicado: (2022)

EuroGEST: Investigating gender stereotypes in multilingual language models
por: Rowe, Jacqueline, et al.
Publicado: (2025)